WebLLM
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| LLM Inference | WebLLM macOS Apple M2 16GB unified memory | Decode Throughput (tok/s)46.4 | 6 | |
| LLM Inference | WebLLM Windows 11 RTX PRO 2000 Blackwell 8GB | Decode Throughput (tok/s)51.1 | 4 |
Showing 2 of 2 rows